Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 3072
    5. 8-RES_FS3072-JB
    6. 1118
    Prev
    Next
    INDEX
    Explanations

    phrases expressing uncertainty or inclusivity

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    739
    +0.10
    0.4%
    614
    +0.10
    0.4%
    649
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    109
    +0.10
    0.05
    242
    +0.10
    0.04
    513
    +0.09
    0.04
    Negative Logits
    isse
    -0.75
    aters
    -0.72
    olis
    -0.72
    arie
    -0.72
    arde
    -0.71
    ciating
    -0.71
    etr
    -0.71
    auri
    -0.71
    és
    -0.70
    agos
    -0.69
    POSITIVE LOGITS
     else
    0.86
     whatsoever
    0.85
    soever
    0.83
     amount
    0.75
     number
    0.71
     extrad
    0.70
     floats
    0.69
     whether
    0.67
     rested
    0.67
     circumstance
    0.67
    Activations Density 0.584%

    No Known Activations